deepinfra.com valid

DeepInfra

For agents: AI inference cloud with OpenAI-compatible API, hundreds of open-source models, embeddings, private GPU deployments and GPU rental. API reference and OpenAPI spe

llm inferenceopenai-compatible apiopen-source modelsgpu deploymentembeddingsprompt caching

Their llms.txt

The beginning of the file, from our validated copy saved 2026-10-23T18:41:12.095Z. Cached copy · Source on deepinfra.com

# DeepInfra

- [What is DeepInfra](https://docs.deepinfra.com/index.md): AI inference cloud — OpenAI-compatible API, 100s of open-source models, private GPU deployments, and GPU rental.
- [Quickstart](https://docs.deepinfra.com/quickstart.md): Make your first API call in 60 seconds — no installation required.
- [Models](https://docs.deepinfra.com/models.md): Browse 200+ open-source models available on DeepInfra.
- [Chat Completions](https://docs.deepinfra.com/chat/overview.md): OpenAI-compatible chat completions API — just change the base URL and model name.
- [Streaming](https://docs.deepinfra.com/chat/streaming.md): Stream chat completion responses token by token using server-sent events.
- [Tool Calling](https://docs.deepinfra.com/chat/tool-calling.md): Let models call external functions — the foundation of AI agents.
- [Structured Outputs](https://docs.deepinfra.com/chat/structured-outputs.md): Get model responses in JSON format using response_format.
- [Vision & OCR](https://docs.deepinfra.com/chat/vision.md): Send images to multimodal models for visual understanding and text extraction.
- [Prompt Caching](https://docs.deepinfra.com/chat/prompt-caching.md): Reduce latency and cost by caching repeated prompt prefixes.
- [Prompt Cache Retention](https://docs.deepinfra.com/chat/prompt-cache-retention.md): Retain a prompt prefix for 5 minutes or 1 hour so reuse skips prefill and bills at the cache-read rate.
- [Reasoning Models](https://docs.deepinfra.com/chat/reasoning.md): Configure chain-of-thought reasoning with reasoning_effort and the reasoning parameter.
- [Log Probabilities](https://docs.deepinfra.com/chat/log-probs.md): Get per-token log probabilities from LLM responses.
- [Text Completions](https://docs.deepinfra.com/apis/completions.md): Legacy OpenAI-compatible completions API for raw text generation.
- [Embeddings](https://docs.deepinfra.com/apis/embeddings.md): Generate embedding vectors from text and images using the OpenAI-compatible embeddings API.
- [Reranking](https://docs.deepinfra.com/apis/reranker.md): Rerank a list of documents by relevance to a query.
- [Image Generation](https://docs.deepinfra.com/apis/image-generation.md): Generate images from text prompts using the OpenAI-compatible images API.
- [Text to Video](https://docs.deepinfra.com/apis/text-to-video.md): Generate video clips from text prompts.
- [Speech Recognition](https://docs.deepinfra.com/apis/speech.md): Transcribe audio to text using Whisper and other speech recognition models.
- [Text to Speech](https://docs.deepinfra.com/apis/text-to-speech.md): Convert text to natural-sounding audio using TTS models.
- [DeepInfra Native API](https://docs.deepinfra.com/apis/deepinfra-native.md): Advanced API with access to all model types including image generation, speech, and zero-shot image classification.
- [Introduction to Batch API](https://docs.deepinfra.com/batch/introduction.md): Run large, non-urgent inference jobs asynchronously at 20% off — OpenAI-compatible
…

Related sites

Find similar publishers by meaning →

Other listed sites in AI and machine learning. See the whole category →

Machine-readable: GET /v1/resolve?q=deepinfra.com · GET /v1/domain/deepinfra.com · this page as Accept: application/json or text/markdown · MCP lookup_domain

Automatically discovered from public files. Inclusion does not imply endorsement or publisher participation.

Claim my listing on Agent Web Map for deepinfra.com:
1. POST https://agentwebmap.com/v1/sites/deepinfra.com/claims and keep claim_id and claim_secret private.
2. Publish the proof: add the line "AgentWebMap ownership: <token>" (token from step 1) to https://deepinfra.com/llms.txt, or use the DNS, meta-tag or well-known method the response describes.
3. POST https://agentwebmap.com/v1/sites/deepinfra.com/verify with {"claim_id": "...", "claim_secret": "..."}.
4. Save the api_key from the answer; it manages the listing (PATCH https://agentwebmap.com/v1/sites/deepinfra.com).
MCP equivalent: tools begin_ownership_claim, then verify_domain, at https://agentwebmap.com/mcp. Docs: https://agentwebmap.com/docs#verify

Corrections or removal requests: contact the directory.